Friday, September 25, 2020

Waterloo Engineering researchers behind an open-source project to detect COVID-19 using chest X-rays and artificial intelligence (AI) announced a significant advancement this week.

In addition to detecting the disease, researchers said their technology is now capable of determining its severity.

Chest x-rays of COVID-19 patients.

Researchers are using AI and chest X-rays to determine COVID-19 severity.

The project, dubbed COVID-Net, was launched in March by researchers at the Vision and Image Processing (VIP) Lab and DarwinAI, a Waterloo startup company co-founded by Alexander Wong, a professor of systems design engineering.

Sheldon Fernandez, a Waterloo Engineering alumnus and CEO of DarwinAI, said in a blog post that the advancement was made using over 10,000 chest X-rays - including hundreds from patients with COVID-19 - in collaboration with doctors at Stony Brook Medicine in New York.

New open-source AI models called COVIDNet-S help doctors triage and prioritize patients for treatment based on the severity of their conditions.

“We have high hopes that COVIDNet-S will be a useful tool in supporting front-line workers throughout the world,” Fernandez wrote in his post.

  1. 2020 (131)
    1. October (17)
    2. September (16)
    3. August (11)
    4. July (13)
    5. June (24)
    6. May (16)
    7. April (11)
    8. March (10)
    9. February (8)
    10. January (5)
  2. 2019 (151)
    1. December (12)
    2. November (17)
    3. October (10)
    4. September (18)
    5. August (11)
    6. July (12)
    7. June (10)
    8. May (14)
    9. April (12)
    10. March (19)
    11. February (10)
    12. January (6)
  3. 2018 (100)
    1. December (6)
    2. November (13)
    3. October (10)
    4. September (6)
    5. August (8)
    6. July (7)
    7. June (11)
    8. May (9)
    9. April (7)
    10. March (14)
    11. February (5)
    12. January (4)
  4. 2017 (124)
  5. 2016 (97)
  6. 2015 (95)
  7. 2014 (133)
  8. 2013 (124)
  9. 2012 (117)
  10. 2011 (95)

Media Contact

Carol Truemner, Communications Officer (email | x33470)